Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Person recognition method and apparatus

a recognition method and person technology, applied in wave based measurement systems, navigation instruments, instruments, etc., can solve problems such as the accuracy of person recognition becoming wors

Active Publication Date: 2011-02-03
FUJIFILM CORP
View PDF26 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Benefits of technology

[0008]An object of the present invention is to provide a person recognition method and apparatus that can precisely recognize a person even if a face image of a registrant registered in a database gets old.
[0015]It is preferable that the person recognition method further include the steps of entering an age of the person to be recognized, calculating a registrant's current age, judging whether or not the difference between the age of the person to be recognized and the registrant's current age is within a predetermined allowance value, and excluding the registrant's personal data from comparison if the difference is out of the predetermined allowance value. This allows reduction in time required for the comparison, and performance of speedy person recognition. The registrant's current age is preferably calculated from a registrant's birthday contained in the personal data and the current date.
[0020]According to the present invention, the number of elapsed years from the date of taking the face image of the registrant registered in the database is calculated, and one of the comparison methods is selected in accordance with the number of elapsed years. This allows the efficient person recognition. Also, the personal data of the cognate of the registrant is accessorily registered, for the purpose of comparing the photographic image not only with the registrant's face image but also with the cognate's face image. Therefore, even if the registrant's face image stored in the database is too old to use, the person recognition is precisely carried out with use of the cognate's face image.

Problems solved by technology

In any of the above apparatuses, the precision of the person recognition becomes worse, as the face image registered into the database gets old.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Person recognition method and apparatus
  • Person recognition method and apparatus
  • Person recognition method and apparatus

Examples

Experimental program
Comparison scheme
Effect test

first embodiment

[0062]In the case of NO in S23, the number N is incremented by one (S24), and the next registrant's personal data is read from the database (S3). In the case of YES in S23, on the other hand, the elapsed year calculator 35 calculates the number of elapsed years Y from the date of taking the face image of the personal data (S4). Since the following sequence is same as that of the first embodiment, description thereof will be omitted.

[0063]In this embodiment, the age of the person to be recognized is inputted in advance, for the purpose of excluding the comparison with the registrant who is much older or younger than the person to be recognized. Therefore, it is possible to shorten time required for the comparison.

third embodiment

[0064]In a third embodiment, the face images, the names and the ages of the top four registrants having the highest degree of resemblance are displayed on a transmissive LCD incorporated in eyeglasses 60. As shown in FIG. 5, a transparent glass 62 about one-third the size of an eyeglass frame 61 is fitted into the single eyeglass frame 61 on a right portion thereof. A transmissive LCD 63 about two-thirds the size of the eyeglass frame 61 is fitted into a remaining area of the eyeglass frame 61. The transmissive LCD 63 is transparent as with the transparent glass 62, when no image is displayed thereon.

[0065]A subminiature CCD camera (not illustrated) is embedded in the eyeglass frame 61, to capture a photographic image of a person 65 to be recognized. The photographic image is sent via a wireless communication system like Bluetooth to a terminal device such as a notebook computer put in a pocket of a jacket or a purse. Instead of the CCD camera, a CMOS camera with a CMOS image sensor...

second embodiment

[0075]In the second embodiment, the allowance value AV is set at five (years old), but may be another value such as three or seven. Instead of the above expression, the following expression may be used:

(A1−A2)2AV)2

[0076]The present invention is applicable to a door phone system. In this case, a person who is approaching a door is automatically detected and photographed, and the face image resemblant to the photographic image is chosen from the database to check who the person is.

[0077]According to the present invention, when the registrant's face image is old, his / her cognate's face image is used in the comparison. Thus, the person recognition apparatus can remind the user of the name of a friend, for example, who has visited the user for the first time in years.

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

Subtracting the date of taking a registrant's face image from the date of taking a photographic image of a person to be recognized, the number of elapsed years Y of the registrant's face image is calculated. If Y<5, an unsophisticated image comparator is selected. If 5≦Y<10, a first face parts comparator is selected to calculate the degree of resemblance between the photographic image and the registrant's face image more precisely than the unsophisticated image comparator. If 10≦Y, a second face parts comparator is selected. If the face image is a child's, the second face parts comparator compares the photographic image not only with the child's face image but also with his / her cognate's face image. After the photographic image is compared with every registrant's face image, the personal data of the top four registrants having the highest degree of resemblance is displayed on an LCD.

Description

BACKGROUND OF THE INVENTION[0001]1. Field of the Invention[0002]The present invention relates to a person recognition method and apparatus that retrieve personal data based on a taken photographic image.[0003]2. Description Related to the Prior Art[0004]Recently, there is a proposed apparatus that not only detects a person's face from a photograph, but also automatically recognizes who the person is (see U.S. Pat. Nos. 6,608,914 and 6,697,505). In this apparatus, characteristic values of features of the face, including the positions of eyes, nose, mouth and the like, extracted from a photographic image of the person to be recognized are compared with those extracted from a face image of a registrant registered in advance in a registered information holding section (database). Then, the registrant having a highest degree of resemblance is outputted as a recognition result.[0005]Since the person's face ages with time, the above apparatus is so designed as to add the newly taken photog...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06K9/00
CPCG06K9/6227G06K9/00288G06V40/172G06V10/87G06F18/285
Inventor EGO, SHUNTA
Owner FUJIFILM CORP
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products